Vals AI Financial Coaching Bench: leaderboard
Financial Coaching Bench v1 (Vals AI, November2026) tests AI financial coaching on 256 private household scenarios. A simulated client, played by Claude Sonnet4.6, answers from a hidden fact sheet; the coach can ask questions and search the web. This board is mean practitioner-checklist credit in percent, preserving each native model and effort. Length-controlled scores and elicitation diagnostics are separate; higher is better.
Metric: Mean practitioner-checklist credit (%). Source: www.vals.ai. Saturation forecast: Not forecast. 27 models tracked. Updated 14 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 5.5 | Max | 76.16 | #5 |
| 2 | Muse Spark 1.2 | xHigh | 75.74 | #97 |
| 3 | Claude Fable 5.1 | Max | 75.71 | #15 |
| 4 | Qwen 3.8 Max | 75.58 | #59 | |
| 5 | MiMo-V2.6-Pro | 75.37 | #76 | |
| 6 | Muse Wonder Full | Max | 74.96 | #17 |
| 7 | Claude Sonnet 5.5 | Max | 74.94 | #19 |
| 8 | GPT-5.6 Sol | Max | 74.89 | #30 |
| 9 | Kimi K3 | Max | 74.53 | #56 |
| 10 | Grok 4.7 | xHigh | 74.07 | #47 |
| 11 | GLM-5.3 | Max | 74.06 | #68 |
| 12 | Muse Wonder | Max | 73.78 | #28 |
| 13 | Gemini 4 Argon | High | 73.13 | #12 |
| 14 | DeepSeek V4.1 Flash | High | 72.83 | #62 |
| 15 | Muse Spark 1.3 | xHigh | 70.99 | #43 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=vals-ai-financial-coaching-bench · How It Works · Data refreshed daily, snapshot 2026-11-16.